Upload model

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: albert-puncapital
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# albert-puncapital
+
+This model is a fine-tuned version of [indobert-lite-base-p2](https://huggingface.co/indobert-lite-base-p2) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.20.0.dev0
+- Pytorch 1.11.0
+- Datasets 2.2.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.15709904239873834,
+    "train_runtime": 1021.7988,
+    "train_samples": 394099,
+    "train_samples_per_second": 771.383,
+    "train_steps_per_second": 12.053
+}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "indobert-lite-base-p2",
+  "architectures": [
+    "AlbertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "finetuning_task": "ner",
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "L",
+    "1": "L-COMMA",
+    "2": "L-EXCLAMATION",
+    "3": "L-PERIOD",
+    "4": "L-QUESTION",
+    "5": "U",
+    "6": "U-COMMA",
+    "7": "U-EXCLAMATION",
+    "8": "U-PERIOD",
+    "9": "U-QUESTION",
+    "10": "UU",
+    "11": "UU-COMMA",
+    "12": "UU-PERIOD",
+    "13": "UU-QUESTION"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "L": 0,
+    "L-COMMA": 1,
+    "L-EXCLAMATION": 2,
+    "L-PERIOD": 3,
+    "L-QUESTION": 4,
+    "U": 5,
+    "U-COMMA": 6,
+    "U-EXCLAMATION": 7,
+    "U-PERIOD": 8,
+    "U-QUESTION": 9,
+    "UU": 10,
+    "UU-COMMA": 11,
+    "UU-PERIOD": 12,
+    "UU-QUESTION": 13
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb4f4c3abca46a16ae5a5bd681dd64e29ab60739d08b6b158a322d216ce16a9
+size 44427351

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "indobert-lite-base-p2",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "indobert-lite-base-p2/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.15709904239873834,
+    "train_runtime": 1021.7988,
+    "train_samples": 394099,
+    "train_samples_per_second": 771.383,
+    "train_steps_per_second": 12.053
+}

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 12316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.7978239688210455e-05,
+      "loss": 0.2689,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.595241961675869e-05,
+      "loss": 0.193,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.392253978564469e-05,
+      "loss": 0.183,
+      "step": 1500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.189265995453069e-05,
+      "loss": 0.1763,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.986278012341669e-05,
+      "loss": 0.1727,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.7832900292302696e-05,
+      "loss": 0.1702,
+      "step": 3000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.5803020461188695e-05,
+      "loss": 0.1678,
+      "step": 3500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.37731406300747e-05,
+      "loss": 0.1645,
+      "step": 4000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.1743260798960706e-05,
+      "loss": 0.1629,
+      "step": 4500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.9713380967846704e-05,
+      "loss": 0.1608,
+      "step": 5000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.768350113673271e-05,
+      "loss": 0.1587,
+      "step": 5500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.565362130561871e-05,
+      "loss": 0.1561,
+      "step": 6000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.362374147450471e-05,
+      "loss": 0.1453,
+      "step": 6500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.1593861643390713e-05,
+      "loss": 0.1399,
+      "step": 7000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9563981812276715e-05,
+      "loss": 0.139,
+      "step": 7500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.7534101981162717e-05,
+      "loss": 0.139,
+      "step": 8000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.5504222150048715e-05,
+      "loss": 0.1382,
+      "step": 8500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3474342318934719e-05,
+      "loss": 0.1381,
+      "step": 9000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.1444462487820721e-05,
+      "loss": 0.1366,
+      "step": 9500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.414582656706723e-06,
+      "loss": 0.1365,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.384702825592725e-06,
+      "loss": 0.1348,
+      "step": 10500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.358882754140955e-06,
+      "loss": 0.1351,
+      "step": 11000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.3290029230269568e-06,
+      "loss": 0.1343,
+      "step": 11500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.2991230919129588e-06,
+      "loss": 0.1339,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "step": 12316,
+      "total_flos": 4101375688441856.0,
+      "train_loss": 0.15709904239873834,
+      "train_runtime": 1021.7988,
+      "train_samples_per_second": 771.383,
+      "train_steps_per_second": 12.053
+    }
+  ],
+  "max_steps": 12316,
+  "num_train_epochs": 2,
+  "total_flos": 4101375688441856.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6042a8df01e4339fe6824eb7b75d8ce70b25363904b3f22bb80fd4e198d7c0
+size 3247